Machine Learning of Infant Spontaneous Movements for the Early Prediction of Cerebral Palsy: A Multi-Site Cohort Study

Background: Early identification of cerebral palsy (CP) during infancy will provide opportunities for early therapies and treatments. The aim of the present study was to present a novel machine-learning model, the Computer-based Infant Movement Assessment (CIMA) model, for clinically feasible early CP prediction based on infant video recordings. Methods: The CIMA model was designed to assess the proportion (%) of CP risk-related movements using a time–frequency decomposition of the movement trajectories of the infant’s body parts. The CIMA model was developed and tested on video recordings from a cohort of 377 high-risk infants at 9–15 weeks corrected age to predict CP status and motor function (ambulatory vs. non-ambulatory) at mean 3.7 years age. The performance of the model was compared with results of the general movement assessment (GMA) and neonatal imaging. Results: The CIMA model had sensitivity (92.7%) and specificity (81.6%), which was comparable to observational GMA or neonatal cerebral imaging for the prediction of CP. Infants later found to have non-ambulatory CP had significantly more CP risk-related movements (median: 92.8%, p = 0.02) compared with those with ambulatory CP (median: 72.7%). Conclusion: The CIMA model may be a clinically feasible alternative to observational GMA.

The Predictive Accuracy of the General Movement Assessment for Cerebral Palsy: A Prospective, Observational Study of High-Risk Infants in a Clinical Follow-Up Setting

Background: Early prediction of cerebral palsy (CP) using the General Movement Assessment (GMA) during the fidgety movements (FM) period has been recommended as standard of care in high-risk infants. The aim of this study was to determine the accuracy of GMA, alone or in combination with neonatal imaging, in predicting cerebral palsy (CP). Methods: Infants with increased risk of perinatal brain injury were prospectively enrolled from 2009–2014 in this multi-center, observational study. FM were classified by two certified GMA observers blinded to the clinical history. Abnormal GMA was defined as absent or sporadic FM. CP-status was determined by clinicians unaware of GMA results. Results: Of 450 infants enrolled, 405 had scorable video and follow-up data until at least 18–24 months. CP was confirmed in 42 (10.4%) children at mean age 3 years 1 month. Sensitivity, specificity, positive and negative predictive values, and accuracy of absent/sporadic FM for CP were 76.2, 82.4, 33.3, 96.8, and 81.7%, respectively. Only three (8.1%) of 37 infants with sporadic FM developed CP. The highest accuracy (95.3%) was achieved by a combination of absent FM and abnormal neonatal imaging. Conclusion: In infants with a broad range of neonatal risk factors, accuracy of early CP prediction was lower for GMA than previously reported but increased when combined with neonatal imaging. Sporadic FM did not predict CP in this study.

An anthropomorphic phantom representing a prematurely born neonate for digital x-ray imaging using 3D printing: Proof of concept and comparison of image quality from different systems

An anthropomorphic phantom for image optimization in neonatal radiography was developed, and its usability in optimizing image acquisition and processing demonstrated. The phantom was designed to mimic a patient image of a prematurely born neonate. A clinical x-ray (neonate <1 kg) taken with an effective dose of 11 µSv on a needle-crystal storage phosphor system was retrospectively selected from anonymized images as an appropriate template representing a standard case in neonatology imaging. The low dose level used in clinical imaging results in high image noise content. Therefore, the image had to be processed using structure preserving noise reduction. Pixel values were related to printing material thickness to result in a similar attenuation pattern as the original patient including support mattress. A 3D model generating a similar x-ray attenuation pattern on an image detector as a patient was derived accounting for beam hardening and perspective, and printed using different printing technologies. Best printing quality was achieved using a laser stereolithography printer. Phantom images from different digital radiography systems used in neonatal imaging were compared. Effects of technology, image processing, and radiation dose on diagnostic image quality can be assessed for otherwise identical anthropomorphic neonatal images not possible with patient images, facilitating optimization and standardization of imaging parameters and image appearance.

Clinical Brain Monitoring with Time Domain NIRS: A Review and Future Perspectives

Near-infrared spectroscopy (NIRS) is an optical technique that can measure brain tissue oxygenation and haemodynamics in real-time and at the patient bedside allowing medical doctors to access important physiological information. However, despite this, the use of NIRS in a clinical environment is hindered due to limitations, such as poor reproducibility, lack of depth sensitivity and poor brain-specificity. Time domain NIRS (or TD-NIRS) can resolve these issues and offer detailed information of the optical properties of the tissue, allowing better physiological information to be retrieved. This is achieved at the cost of increased instrument complexity, operation complexity and price. In this review, we focus on brain monitoring clinical applications of TD-NIRS. A total of 52 publications were identified, spanning the fields of neonatal imaging, stroke assessment, traumatic brain injury (TBI) assessment, brain death assessment, psychiatry, peroperative care, neuronal disorders assessment and communication with patient with locked-in syndrome. In all the publications, the advantages of the TD-NIRS measurement to (1) extract absolute values of haemoglobin concentration and tissue oxygen saturation, (2) assess the reduced scattering coefficient, and (3) separate between extra-cerebral and cerebral tissues, are highlighted; and emphasize the utility of TD-NIRS in a clinical context. In the last sections of this review, we explore the recent developments of TD-NIRS, in terms of instrumentation and methodologies that might impact and broaden its use in the hospital.

NeBSS: Semi-Automated Parcellation of Neonatal Structural Brain MRI

1) Introduction: Brain parcellation is an important processing step in the analysis of structural brain MRI. Existing software implementations are optimized for fully developed adult brains, and provide inadequate results when applied to neonatal brain imaging. 2) Methods: We developed a semi-automated pipeline, NeBSS, for extracting 50 discrete brain structures from neonatal brain MRI, using an atlas registration method that leverages the existing ALBERT neonatal atlas 3) Results: We demonstrate a simple linear workflow for neonatal brain parcellation. NeBSS is robust to variation in imaging acquisition protocol and magnet field strength. 4) Conclusion: NeBSS is a robust pipeline capable of parcellating neonatal brain MRIs using a simple processing workflow. NeBSS fills a need in clinical translational research in neonatal imaging, where existing automated or semi-automated implementations are too rigid to be successfully applied to multi-center neuroprotection studies and clinically heterogeneous cohorts. The software is open source and freely available.